Classic4Children: Adapting Chinese Literary Classics for Children with Large Language Model

2025-02-03

AI Summary

This study addresses the challenge of children’s limited comprehension of classical Chinese literature due to its archaic language and intricate narrative structures, proposing the novel task of Child-Friendly Literary Adaptation (CLA). Methodologically, it introduces the first integrated framework combining character personality modeling, narrative structure guidance, and a readability reward mechanism, augmented by a lookahead decoding strategy. The technical pipeline encompasses fine-grained instruction tuning, structured prompt engineering, reinforcement learning for human preference alignment, and a custom readability evaluator. Experiments on our bilingual Classic4Children dataset—curated from the Four Great Classical Novels—demonstrate substantial improvements in both automated and human evaluations: generated adaptations exhibit strong child appeal, coherent logic, linguistic appropriateness for upper elementary readers (Grades 4–6), and embedded moral, historical, and humanistic educational value.

Technology Category

• Natural Language Processing: Generation
• Humans and AI: Learning Human Values and Preferences
• Cognitive Modeling & Cognitive Systems: Adaptive Behavior

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Chinese literary classics hold significant cultural and educational value, offering deep insights into morality, history, and human nature. These works often include classical Chinese and complex narratives, making them difficult for children to read. To bridge this gap, we introduce a child-friendly literary adaptation (CLA) task to adapt the Chinese literary classic into engaging and accessible text for children. However, recent large language models (LLMs) overlook children's reading preferences (ie, vivid character portrayals, concise narrative structures, and appropriate readability), which poses challenges in CLA. In this paper, we propose a method called InstructChild, which augments the LLM with these preferences for adaptation. Specifically, we first obtain the characters' personalities and narrative structure as additional information for fine-grained instruction tuning. Then, we devise a readability metric as the reward to align the LLM with the children's reading level. Finally, a lookahead decoding strategy is applied to improve the readability of the generated text during inference. To support the evaluation of CLA task, we construct the Classic4Children dataset, which comprises both the original and child-friendly versions of the Four Great Classical Novels of Chinese literature. Experimental results show that our InstructChild significantly improves automatic and human evaluation performance.

Problem

• Language Models
• Children's Literature
• Adaptation of Classic Literature

Innovation

• InstructChild method
• Children's literature adaptation
• Large language model simplification